CN115994136A - Energy data cleaning method and system based on energy network topological relation - Google Patents
Energy data cleaning method and system based on energy network topological relation Download PDFInfo
- Publication number
- CN115994136A CN115994136A CN202310037977.XA CN202310037977A CN115994136A CN 115994136 A CN115994136 A CN 115994136A CN 202310037977 A CN202310037977 A CN 202310037977A CN 115994136 A CN115994136 A CN 115994136A
- Authority
- CN
- China
- Prior art keywords
- energy
- monitoring
- time
- branch
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention provides an energy data cleaning method and system based on an energy network topological relation, wherein the method comprises the following steps: installing corresponding switch state trackers on each branch node switch of the energy network to form an initial switch branch topological graph; according to the switching states of the branch nodes collected in real time by each switching state tracker, a switching branch real-time topological graph is obtained and uploaded to an energy monitoring system, and an energy network real-time topological relation graph is generated by the switching branch real-time topological graph; in response to the change of the switching state of the branch node, updating the switching branch real-time topological graph by a switching state tracker, and uploading the switching branch real-time topological graph to an energy monitoring system to update an energy network real-time topological relation graph; and comparing the switch branch real-time topological graph obtained at fixed time with the energy network real-time topological relation graph, and cleaning corresponding energy data according to the obtained topological relation comparison result to obtain effective energy data. The method and the device can timely and effectively monitor and correct the abnormal data from the energy network structure, and improve the accuracy of the data.
Description
Technical Field
The invention relates to the technical field of energy monitoring, in particular to an energy data cleaning method and system based on an energy network topological relation.
Background
With the large-scale investment of intelligent equipment in the energy field in recent years, an energy network is increasingly complex, operation data generated in an energy monitoring system are exponentially increased, and the accuracy of the topology relation data of the energy network determines the mining value of the energy data. How to clean the energy data effectively, and further improve the quality of the energy data has become a key technology for enthusiastically researching the field of energy data mining.
At present, the energy data cleaning method mainly comprises the following steps: and checking and repairing abnormal data by using a fuzzy rule satisfaction classifier, performing cluster analysis by using a distributed big data platform, manually checking an energy monitoring instrument database on site, and the like. Although the existing energy data cleaning method can improve the quality of energy data to a certain extent, the corresponding application defects still exist, and the abnormal data of the energy network topology cannot be really and timely corrected effectively:
(1) And (3) manual field verification: the workload is extremely large, the efficiency is low, the data abnormality cannot be found timely, small and unobvious abnormal data is easy to ignore, and the reliability is poor.
(2) The distributed big data platform clustering analysis method comprises the following steps: the method is mainly used for data cleaning in the field of distributed energy sources, and has a narrow application range.
(3) The fuzzy rule satisfaction classifier test repair method and the energy monitoring instrument database method: both the two methods clean data from the aspects of data dispersion, deletion degree and the like, and the data in the aspect of energy network topology is not processed.
Therefore, there is a need to provide a simple, efficient and general energy data cleaning method, which can timely and effectively monitor and correct abnormal energy data, and improve the accuracy of the energy data.
Disclosure of Invention
The invention aims to provide an energy data cleaning method based on an energy network topological relation, which solves the application defect of the existing energy cleaning method by monitoring and correcting abnormal energy data from an energy network structure, can effectively monitor and correct the energy network topological abnormal data in time, improves the accuracy of the energy data and further improves the application value of the energy data.
In order to achieve the above objective, it is necessary to provide an energy data cleaning method and system based on an energy network topology relationship.
In a first aspect, an embodiment of the present invention provides an energy data cleaning method based on an energy network topology relationship, where the method includes the following steps:
installing corresponding switch state trackers on each branch node switch of the energy network, and generating corresponding initial switch branch topological diagrams;
obtaining a switch branch real-time topological graph according to the switch states of the branch nodes and the corresponding initial switch branch topological graph acquired in real time by each switch state tracker;
uploading the switch branch real-time topological graph to an energy monitoring system, and obtaining an energy network real-time topological relation graph by the energy monitoring system according to each switch state tracker and the corresponding switch branch real-time topological graph;
responding to the change of the switching state of the branch node, updating a corresponding switching branch real-time topological graph by the switching state tracker, and uploading the updated switching branch real-time topological graph to the energy monitoring system so that the energy monitoring system updates the energy network real-time topological relation graph;
the switch branch real-time topological graph of each switch state tracker is obtained at fixed time, and the switch branch real-time topological graph is compared with the energy network real-time topological relation graph to obtain a topological relation comparison result;
and cleaning the corresponding energy data according to the topological relation comparison result to obtain effective energy data.
Further, the step of cleaning the corresponding energy data according to the topological relation comparison result to obtain the effective energy data includes:
if the topological relation comparison result is the same, judging that the current energy data is effective energy data, and cleaning is not needed;
if the topological relation comparison result is inconsistent, judging that abnormal data exists in the current energy data, acquiring monitoring data of a switch branch and a contralateral switch corresponding to the abnormal data, comparing the monitoring data with a background database of the energy monitoring system, and cleaning the corresponding energy data according to the corresponding data comparison result to obtain effective energy data; the monitoring data includes time, voltage, current, pressure and flow.
Further, the step of cleaning the corresponding energy data according to the corresponding data comparison result to obtain the effective energy data includes:
if the data comparison result is inconsistent, acquiring the monitoring quantity of the abnormal time of the upstream branch master switch and the abnormal time of all the corresponding downstream branch switches, and comparing to obtain a monitoring quantity comparison result; the monitored quantity includes current and flow;
and cleaning the corresponding energy data according to the monitoring comparison result to obtain effective energy data.
Further, the step of obtaining the monitoring comparison result includes:
and if the monitoring quantity of the upstream branch switch is equal to the sum of all corresponding monitoring quantities of the downstream branch switches, judging that the comparison results of the monitoring quantities are consistent, otherwise, judging that the comparison results of the monitoring quantities are inconsistent.
Further, the step of cleaning the corresponding energy data according to the monitoring comparison result to obtain effective energy data includes:
and if the comparison result of the monitoring quantity is consistent, updating a background database of the energy monitoring system according to the monitoring data of the switch state tracker, otherwise, judging that missing data exists, and carrying out missing filling processing on the abnormal time monitoring quantity according to data similarity matching to obtain the effective energy data.
Further, the step of performing missing filling processing on the abnormal time monitoring amount according to data similarity matching to obtain the effective energy data includes:
acquiring a history monitoring quantity set of the upstream branch master switch and all downstream branch switches corresponding to the current energy network real-time topological relation diagram after switching, and acquiring a monitoring quantity similarity set according to the history monitoring quantity set and the abnormal moment monitoring quantity; the history monitoring set comprises history monitoring values at a plurality of sampling moments;
obtaining a missing data ratio of the monitoring quantity at the abnormal moment according to the historical monitoring quantity corresponding to the maximum monitoring quantity similarity in the monitoring quantity similarity set;
obtaining the total quantity of missing values of the abnormal time monitoring quantity according to the abnormal time monitoring quantity;
and obtaining each missing value according to the total missing value and the missing data ratio, and filling the abnormal time monitoring quantity according to the missing value to obtain the effective energy data.
Further, the step of obtaining a data similarity set according to the history monitoring set and the abnormal time monitoring set includes:
calculating attribute similarity between each history monitoring amount and the abnormal moment monitoring amount; the attribute similarity comprises the similarity of the monitoring quantity of the total switch of the upstream branch and the similarity of the monitoring quantity of the switches of all the corresponding downstream branches; the attribute similarity is expressed as:
in the method, in the process of the invention,
d i (x i ,x i ')＝|x i -x i '|
d max ＝max{d i (x i ,x i '),i＝1,2,...,n}
wherein x is i And x i 'represents the ith attribute value of the abnormal moment monitoring quantity x and the history monitoring quantity x', respectively; d, d i (x i ,x i ' indicates x i And x i ' absolute value of attribute deviation; d, d max The maximum attribute deviation absolute value of the abnormal moment monitoring quantity x and the historical monitoring quantity x' is represented; s is S i (x i ,x i ') represents the attribute similarity of the ith attribute value of the abnormal moment monitoring quantity x and the history monitoring quantity x'; n represents the total number of attributes of the abnormal time monitoring quantity x and the history monitoring quantity x';
obtaining the corresponding monitoring quantity similarity according to the attribute similarity and the corresponding missing mark; the monitoring amount similarity is expressed as:
wherein Sim (x, x ') represents the similarity of the monitored quantity of the abnormal moment monitored quantity x and the historical monitored quantity x'; epsilon i And the missing mark of the ith attribute in the abnormal moment monitoring quantity is indicated.
In a second aspect, an embodiment of the present invention provides an energy data cleaning system based on an energy network topology relationship, where the system includes:
the initial topology construction module is used for installing the corresponding switch state trackers on the switches of all branch nodes of the energy network and generating a corresponding initial switch branch topology diagram;
the real-time topology construction module is used for obtaining a switch branch real-time topological graph according to the switch states of the branch nodes and the corresponding initial switch branch topological graph, which are acquired in real time by each switch state tracker;
the network topology construction module is used for uploading the switch branch real-time topological graph to an energy monitoring system, and the energy monitoring system obtains an energy network real-time topological relation graph according to each switch state tracker and the corresponding switch branch real-time topological graph;
the topological relation updating module is used for responding to the change of the switching state of the branch node, updating a corresponding switching branch real-time topological graph by the switching state tracker, and uploading the updated switching branch real-time topological graph to the energy monitoring system so that the energy monitoring system updates the energy network real-time topological relation graph;
the topological relation comparison module is used for acquiring the switch branch real-time topological graph of each switch state tracker at fixed time, and comparing the switch branch real-time topological graph with the energy network real-time topological relation graph to obtain a topological relation comparison result;
and the energy data cleaning module is used for cleaning the corresponding energy data according to the topological relation comparison result to obtain effective energy data.
In a third aspect, embodiments of the present invention further provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect, embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above method.
The application provides an energy data cleaning method and system based on an energy network topological relation, by the method, the method is used for forming an initial switch branch topological diagram by installing corresponding switch state trackers of all branch node switches of an energy network, obtaining switch branch real-time topological diagrams according to the branch node switch states acquired by all switch state trackers in real time, uploading the switch branch real-time topological diagrams to an energy monitoring system, generating an energy network real-time topological relation diagram by the energy monitoring system, updating the switch branch real-time topological diagrams by the switch state trackers in response to the change of the branch node switch states, uploading the switch branch real-time topological diagrams to the energy monitoring system, updating the energy network real-time topological relation diagram, and comparing the switch branch real-time topological diagrams with the energy network real-time topological relation diagrams to obtain a topological relation comparison result, and cleaning corresponding energy data according to the topological relation comparison result to obtain the technical scheme of effective energy data. Compared with the prior art, the energy data cleaning method based on the energy network topological relation solves the application defect of the existing energy data cleaning method, is simple, efficient and universal, can timely and effectively monitor data abnormality on an energy network structure, automatically correct abnormal data, realize cleaning from the most basic energy network topological relation data, provide guarantee for the accuracy of the energy data, and further improve the application value of the energy data.
Drawings
Fig. 1 is a schematic diagram of an application scenario of an energy data cleaning method based on an energy network topology relationship in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an architecture for energy data cleaning based on an energy network topology in an embodiment of the present invention;
FIG. 3 is a flow chart of an energy data cleaning method based on an energy network topology relationship in an embodiment of the invention;
FIG. 4 is a schematic diagram of an energy network topology in an embodiment of the present invention;
FIG. 5 is a schematic flow chart of performing missing fill processing on abnormal time monitoring according to data similarity matching in an embodiment of the present invention;
FIG. 6 is a schematic diagram of an energy data cleaning system based on an energy network topology in an embodiment of the present invention;
fig. 7 is an internal structural view of a computer device in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantageous effects of the present application more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples, and it should be understood that the examples described below are only illustrative of the present invention and are not intended to limit the scope of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides an energy data cleaning method for monitoring and correcting abnormal energy data from an energy network structure, which considers the situation that the existing energy network is frequent in change, a large amount of network topology abnormal data cannot be effectively monitored and the abnormal data cannot be timely and effectively corrected by adopting the existing data cleaning method. The method can be applied to the terminal and the server shown in fig. 1. The terminal may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers and portable wearable devices, and the server may be implemented by a separate server or a server cluster formed by a plurality of servers. The server can clean the energy data in real time by adopting the energy data anomaly monitoring and anomaly correcting method realized by the energy network topology relation automatic generation technology based on energy flow formation and the branch node switch topology state automatic tracking technology according to the architecture shown in fig. 2, and the obtained effective energy data is used for subsequent research of the server or is sent to the terminal for the user of the terminal to check and analyze. The following examples will explain the energy data cleaning method based on the energy network topology relationship of the present invention in detail.
In one embodiment, as shown in fig. 3, there is provided an energy data cleaning method based on an energy network topology relationship, including the steps of:
s11, installing corresponding switch state trackers on each branch node switch of the energy network, and generating a corresponding initial switch branch topological graph; the switch state tracker is mainly capable of realizing the functions required by the application, and is not particularly limited herein;
s12, obtaining a switch branch real-time topological graph according to the switch states of the branch nodes and the corresponding initial switch branch topological graph, which are acquired in real time by each switch state tracker; the switch branch real-time topological graph can be understood as an initial switch branch topological graph corresponding to the update of the switch state of the branch node acquired in real time by the switch state tracker, and a real-time topological graph corresponding to the switch state tracker is obtained;
s13, uploading the switch branch real-time topological graph to an energy monitoring system, and obtaining an energy network real-time topological relation graph by the energy monitoring system according to each switch state tracker and the corresponding switch branch real-time topological graph; the real-time topology relation diagram of the energy network is shown in fig. 4, and is obtained by combining the energy path matching according to the first identification IP of each switch state tracker and the second identification IP of each switch branch real-time topology diagram, and in principle, the real-time topology relation diagram of the whole energy network can be updated and adjusted in real time along with the real-time change of the switch state of each branch node.
S14, responding to the change of the switching state of the branch node, updating a corresponding switching branch real-time topological graph by the switching state tracker, and uploading the updated switching branch real-time topological graph to the energy monitoring system so that the energy monitoring system updates the energy network real-time topological relation graph; the process of updating the corresponding switch branch real-time topological graph by the switch state tracker can be understood as that when the switch state of a certain branch node on the energy network changes, the switch state tracker arranged on the switch valve is used for switching to the corresponding branch topological relationship in real time after monitoring the change, and the updated switch branch real-time topological graph is obtained; meanwhile, the energy monitoring system can also update and record the existing energy network real-time topological relation diagram in the background database according to the updated switch branch real-time topological diagram reported by the switch traditional tracker.
It should be noted that, the energy data stored in the background database of the energy monitoring system is obtained through the data reporting mode of the switch state tracker provided by the method steps, in principle, the energy data stored in the background database of the energy monitoring system should be accurate, but in the actual running process of the energy monitoring system, the situations of poor communication, overlarge data quantity or incapacity of the background server performance and the like are easy to occur, and the situation of partial energy data storage loss is caused. In order to ensure the accuracy of the energy data, the abnormality of the energy data needs to be monitored and corrected in real time, and the following method steps are preferably adopted in the embodiment to timely and effectively monitor and clean the energy data based on the energy network topological relation.
S15, the switch branch real-time topological graph of each switch state tracker is obtained at fixed time, and the switch branch real-time topological graph is compared with the energy network real-time topological relation graph to obtain a topological relation comparison result; the process of obtaining the topological relation comparison result can be understood as that the energy monitoring system regularly calls the switch branch real-time topological graph stored by the switch state tracker of each branch node switch in the energy network according to a preset monitoring period, and performs one-to-one comparison analysis on the switch branch real-time topological graph and the data stored in the background database of the energy monitoring system so as to obtain a judging result of whether the data is inconsistent.
S16, cleaning the corresponding energy data according to the topological relation comparison result to obtain effective energy data; the process of obtaining effective energy data can be understood as a process of analyzing abnormal energy data in a topological relation comparison result according to monitoring data including time, voltage, current, pressure and flow of a switch branch and a contralateral switch corresponding to the obtained abnormal data, comparing and analyzing the obtained abnormal time monitoring values including current and flow of an upstream branch master switch and all downstream branch switches corresponding to abnormal time, and cleaning the energy data in a targeted manner according to different analysis results.
Specifically, the step of cleaning the corresponding energy data according to the topological relation comparison result to obtain the effective energy data includes:
if the topological relation comparison result is the same, judging that the current energy data is effective energy data, and cleaning is not needed;
if the topological relation comparison result is inconsistent, judging that abnormal data exists in the current energy data, acquiring monitoring data of a switch branch and a contralateral switch corresponding to the abnormal data, comparing the monitoring data with a background database of the energy monitoring system, and cleaning the corresponding energy data according to the corresponding data comparison result to obtain effective energy data; the process of obtaining the data comparison result can be understood as a process of comparing abnormal data inconsistent with the topological relation, and further comparing and analyzing monitoring data such as time, voltage, current, pressure, flow and the like of the associated branch with corresponding data stored in a background database; it should be noted that, the comparison herein is to compare time, voltage, current, pressure and flow, and the corresponding data comparison results are equally divided into two cases of coincidence and non-coincidence (partial non-coincidence or all non-coincidence), and then classification processing is performed according to the difference of the data comparison results, specifically, the step of cleaning the corresponding energy data according to the corresponding data comparison results to obtain the effective energy data includes:
if the data comparison result is inconsistent, acquiring the monitoring quantity of the abnormal time of the upstream branch master switch and the abnormal time of all the corresponding downstream branch switches, and comparing to obtain a monitoring quantity comparison result; the monitored quantity includes current and flow; the process of obtaining the monitoring comparison result can be understood as a process of judging whether the flow of the upstream branch circuit total switch is equal to the sum of the flow corresponding to all the downstream branch circuit switches, and judging whether the current of the upstream branch circuit total switch is equal to the sum of the current corresponding to all the downstream branch circuit switches, so as to obtain an analysis result; specifically, the step of obtaining the monitoring comparison result includes:
if the monitoring quantity of the upstream branch switch is equal to the sum of the monitoring quantity of all the corresponding downstream branch switches, judging that the comparison results of the monitoring quantity are consistent, otherwise, judging that the comparison results of the monitoring quantity are inconsistent;
as shown in fig. 3, the monitored quantity (current or flow) acquired by the upstream branch master switch H at time T is denoted as I, and the downstream branch switch H corresponding thereto 1 、H 2 And H 3 The monitored quantity (current or flow) acquired at time T is recorded as I 1 、I 2 And I 3 The method comprises the steps of carrying out a first treatment on the surface of the If the formula (1) is satisfied, determining that the energy data in the background database of the energy monitoring system is abnormal, and performing coverage update on the related data in the background database by using the energy data information monitored by the corresponding switch state tracker. If the following formula is not satisfied, judging that the data is missing abnormal, and further processing missing data to ensure that the data is accurately available.
I＝I 1 +I 2 +I 3 (1)
According to the monitoring comparison result, cleaning the corresponding energy data to obtain effective energy data; the monitoring comparison results are divided into two conditions of coincidence and non-coincidence (partial non-coincidence or all non-coincidence), and then classification processing is carried out according to the difference of the monitoring comparison results; specifically, the step of cleaning the corresponding energy data according to the monitoring comparison result to obtain the effective energy data includes:
if the comparison result of the monitoring quantity is consistent, updating a background database of the energy monitoring system according to the monitoring data of the switch state tracker, otherwise, judging that missing data exists, and carrying out missing filling processing on the monitoring quantity at the abnormal moment according to data similarity matching to obtain the effective energy data;
the monitoring amount of abnormal time can be understood as a data set comprising an upstream branch master switch and monitoring amounts corresponding to all downstream branch switches, and the monitoring amount corresponding to each switch can be regarded as an attribute of the data set; correspondingly, the data similarity matching process can be understood as firstly calculating the similarity of each attribute of the monitoring quantity at the abnormal moment and all the historical monitoring quantities of the upstream branch master switches and all the corresponding downstream branch switches under the real-time topological relation diagram of the same energy network, then calculating the similarity of the whole monitoring quantity, and determining the missing data in the monitoring quantity at the abnormal moment according to the similarity of the maximum monitoring quantity and filling; specifically, as shown in fig. 5, the step of performing missing filling processing on the abnormal time monitoring value according to data similarity matching to obtain the effective energy data includes:
acquiring a history monitoring quantity set of the upstream branch master switch and all downstream branch switches corresponding to the current energy network real-time topological relation diagram after switching, and acquiring a monitoring quantity similarity set according to the history monitoring quantity set and the abnormal moment monitoring quantity; the historical monitoring set can be understood as a plurality of groups of monitoring data extracted according to a preset step length, including historical monitoring values at a plurality of sampling moments; the step of obtaining the data similarity set according to the history monitoring set and the abnormal moment monitoring value comprises the following steps:
calculating attribute similarity between each history monitoring amount and the abnormal moment monitoring amount; the attribute similarity comprises the similarity of the monitoring quantity of the total switch of the upstream branch and the similarity of the monitoring quantity of the switches of all the corresponding downstream branches; the attribute similarity is expressed as:
in the method, in the process of the invention,
d i (x i ,x i ')＝|x i -x i '|
d max ＝max{d i (x i ,x i '),i＝1,2,...,n}
wherein x is i And x i 'represents the ith attribute value of the abnormal moment monitoring quantity x and the history monitoring quantity x', respectively; d, d i (x i ,x i ' indicates x i And x i ' absolute value of attribute deviation; d, d max The maximum attribute deviation absolute value of the abnormal moment monitoring quantity x and the historical monitoring quantity x' is represented; s is S i (x i ,x i ') represents the attribute similarity of the ith attribute value of the abnormal moment monitoring quantity x and the history monitoring quantity x'; n represents the total number of attributes of the abnormal time monitoring quantity x and the history monitoring quantity x';
obtaining the corresponding monitoring quantity similarity according to the attribute similarity and the corresponding missing mark; the monitoring amount similarity is expressed as:
wherein Sim (x, x ') represents the similarity of the monitored quantity of the abnormal moment monitored quantity x and the historical monitored quantity x'; epsilon i Missing marks representing the ith attribute in the anomaly monitoring quantity, if ε i Equal to 1, indicating that the ith attribute value is complete, if ε i Equal to 0, indicating that the ith attribute value does not exist;
obtaining a missing data ratio of the monitoring quantity at the abnormal moment according to the historical monitoring quantity corresponding to the maximum monitoring quantity similarity in the monitoring quantity similarity set;
obtaining the total quantity of missing values of the abnormal time monitoring quantity according to the abnormal time monitoring quantity;
obtaining each missing value according to the total missing value and the missing data ratio, and filling the abnormal time monitoring quantity according to the missing value to obtain the effective energy data;
specifically, the process of filling the abnormal time monitoring amount is described by taking the energy network topology structure shown in fig. 4 as an example: assuming abnormal timeMonitoring middle I 1 And I 3 Missing, and the historical monitoring quantity corresponding to the maximum monitoring quantity similarity is { I', I } 1 ',I' 2 ,I 3 ' then I can be calculated 1 'and I' 3 Is denoted as alpha 1 :α 3 Taking the obtained ratio as a missing data ratio of the abnormal moment monitoring quantity; meanwhile, the total missing value can be obtained according to abnormal time monitoring: i Lack of supply ＝I-I 2 The method comprises the steps of carrying out a first treatment on the surface of the Then, based on the determined total missing value and missing data ratio, a desired missing value can be obtained according to the following formula (2):
the missing value I can be obtained according to formula (2) 1 And I 3 And can fill missing data for the abnormal time monitoring quantity; it should be noted that the foregoing missing value calculation process is only an exemplary description, and in practical application, there may be a process where one upstream total switch corresponds to more branch switches, and the corresponding missing value may be obtained only by referring to the foregoing steps to obtain the corresponding missing value total and the missing data proportion according to the actual situation, and then calculating with reference to the missing total allocation method of the formula (2).
According to the method, the device and the system, the corresponding switch state trackers are installed on the branch node switches of the energy network to form an initial switch branch topological graph, the switch branch real-time topological graph is obtained according to the branch node switch states acquired by the switch state trackers in real time and uploaded to the energy monitoring system, after the switch state trackers generate the energy network real-time topological relation graph, the switch state trackers update the switch branch real-time topological graph and upload to the energy monitoring system to update the energy network real-time topological relation graph in response to the change of the branch node switch states, the switch branch real-time topological graph is obtained at regular time and compared with the energy network real-time topological relation graph to obtain a topological relation comparison result, and the corresponding energy data is classified and cleaned according to the topological relation comparison result to obtain effective energy data.
In one embodiment, as shown in fig. 6, there is provided an energy data cleansing system based on an energy network topology, the system comprising:
the initial topology construction module 1 is used for installing corresponding switch state trackers on each branch node switch of the energy network and generating a corresponding initial switch branch topological diagram;
the real-time topology construction module 2 is used for obtaining a switch branch real-time topological graph according to the switch states of the branch nodes and the corresponding initial switch branch topological graph acquired in real time by each switch state tracker;
the network topology construction module 3 is used for uploading the switch branch real-time topological graph to an energy monitoring system, and the energy monitoring system obtains an energy network real-time topological relation graph according to each switch state tracker and the corresponding switch branch real-time topological graph;
the topology relation updating module 4 is configured to respond to the change of the switching state of the branch node, update a corresponding switching branch real-time topology map by using the switching state tracker, and upload the updated switching branch real-time topology map to the energy monitoring system, so that the energy monitoring system updates the energy network real-time topology relation map;
the topological relation comparison module 5 is used for acquiring the switch branch real-time topological graph of each switch state tracker at fixed time, and comparing the switch branch real-time topological graph with the energy network real-time topological relation graph to obtain a topological relation comparison result;
and the energy data cleaning module 6 is used for cleaning the corresponding energy data according to the topological relation comparison result to obtain effective energy data.
Specific limitation regarding an energy data cleaning system based on an energy network topology may be referred to above as limitation regarding an energy data cleaning method based on an energy network topology, and will not be described herein. The modules in the energy data cleaning system based on the energy network topological relation can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Fig. 7 shows an internal structural diagram of a computer device, which may be a terminal or a server in particular, in one embodiment. As shown in fig. 7, the computer device includes a processor, a memory, a network interface, a display, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is configured to implement a method for cleaning energy data based on an energy network topology. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those of ordinary skill in the art that the architecture shown in fig. 7 is merely a block diagram of some of the architecture relevant to the present application and is not intended to limit the computer device on which the present application may be implemented, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have the same arrangement of components.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when the computer program is executed.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, implements the steps of the above method.
In summary, the energy data cleaning method and system based on the energy network topological relation provided by the embodiment of the invention realize that each branch node switch of the energy network is installed with a corresponding switch state tracker to form an initial switch branch topological diagram, the switch branch real-time topological diagram is obtained according to the branch node switch states acquired by each switch state tracker in real time and is uploaded to an energy monitoring system, after the energy network real-time topological relation diagram is generated by the switch state tracker, the switch state tracker updates the switch branch real-time topological diagram to the energy monitoring system to update the energy network real-time topological relation diagram in response to the change of the branch node switch states, the switch branch real-time topological diagram is regularly acquired to be compared with the energy network real-time topological relation diagram to obtain a topological relation comparison result, and the corresponding energy data is classified and cleaned according to the topological relation comparison result to obtain the technical scheme of the effective energy data.
In this specification, each embodiment is described in a progressive manner, and all the embodiments are directly the same or similar parts referring to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments. It should be noted that, any combination of the technical features of the foregoing embodiments may be used, and for brevity, all of the possible combinations of the technical features of the foregoing embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few preferred embodiments of the present application, which are described in more detail and are not thereby to be construed as limiting the scope of the invention. It should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and substitutions should also be considered to be within the scope of the present application. Therefore, the protection scope of the patent application is subject to the protection scope of the claims.
Claims (10)
1. An energy data cleaning method based on an energy network topological relation is characterized by comprising the following steps:
installing corresponding switch state trackers on each branch node switch of the energy network, and generating corresponding initial switch branch topological diagrams;
obtaining a switch branch real-time topological graph according to the switch states of the branch nodes and the corresponding initial switch branch topological graph acquired in real time by each switch state tracker;
uploading the switch branch real-time topological graph to an energy monitoring system, and obtaining an energy network real-time topological relation graph by the energy monitoring system according to each switch state tracker and the corresponding switch branch real-time topological graph;
responding to the change of the switching state of the branch node, updating a corresponding switching branch real-time topological graph by the switching state tracker, and uploading the updated switching branch real-time topological graph to the energy monitoring system so that the energy monitoring system updates the energy network real-time topological relation graph;
the switch branch real-time topological graph of each switch state tracker is obtained at fixed time, and the switch branch real-time topological graph is compared with the energy network real-time topological relation graph to obtain a topological relation comparison result;
and cleaning the corresponding energy data according to the topological relation comparison result to obtain effective energy data.
2. The energy data cleaning method based on the topological relation of the energy network according to claim 1, wherein the step of cleaning the corresponding energy data according to the topological relation comparison result to obtain the effective energy data comprises the following steps:
if the topological relation comparison result is the same, judging that the current energy data is effective energy data, and cleaning is not needed;
if the topological relation comparison result is inconsistent, judging that abnormal data exists in the current energy data, acquiring monitoring data of a switch branch and a contralateral switch corresponding to the abnormal data, comparing the monitoring data with a background database of the energy monitoring system, and cleaning the corresponding energy data according to the corresponding data comparison result to obtain effective energy data; the monitoring data includes time, voltage, current, pressure and flow.
3. The energy data cleaning method based on the energy network topology according to claim 2, wherein the step of cleaning the corresponding energy data according to the corresponding data comparison result to obtain the effective energy data comprises:
if the data comparison result is inconsistent, acquiring the monitoring quantity of the abnormal time of the upstream branch master switch and the abnormal time of all the corresponding downstream branch switches, and comparing to obtain a monitoring quantity comparison result; the monitored quantity includes current and flow;
and cleaning the corresponding energy data according to the monitoring comparison result to obtain effective energy data.
4. The energy data cleaning method based on the topological relation of the energy network according to claim 3, wherein the step of obtaining the monitoring comparison result by comparing the monitoring quantity of the upstream branch master switch at the abnormal moment with the monitoring quantity of the abnormal moment corresponding to all the downstream branch switches comprises the following steps:
and if the monitoring quantity of the upstream branch switch is equal to the sum of all corresponding monitoring quantities of the downstream branch switches, judging that the comparison results of the monitoring quantities are consistent, otherwise, judging that the comparison results of the monitoring quantities are inconsistent.
5. The energy data cleaning method based on the topological relation of the energy network as set forth in claim 3, wherein the step of cleaning the corresponding energy data according to the comparison result of the monitoring to obtain the effective energy data comprises the steps of:
and if the comparison result of the monitoring quantity is consistent, updating a background database of the energy monitoring system according to the monitoring data of the switch state tracker, otherwise, judging that missing data exists, and carrying out missing filling processing on the abnormal time monitoring quantity according to data similarity matching to obtain the effective energy data.
6. The energy data cleaning method based on the energy network topology according to claim 5, wherein the step of performing the missing filling process on the abnormal time supervision according to the data similarity matching to obtain the effective energy data includes:
acquiring a history monitoring quantity set of the upstream branch master switch and all downstream branch switches corresponding to the current energy network real-time topological relation diagram after switching, and acquiring a monitoring quantity similarity set according to the history monitoring quantity set and the abnormal moment monitoring quantity; the history monitoring set comprises history monitoring values at a plurality of sampling moments;
obtaining a missing data ratio of the monitoring quantity at the abnormal moment according to the historical monitoring quantity corresponding to the maximum monitoring quantity similarity in the monitoring quantity similarity set;
obtaining the total quantity of missing values of the abnormal time monitoring quantity according to the abnormal time monitoring quantity;
and obtaining each missing value according to the total missing value and the missing data ratio, and filling the abnormal time monitoring quantity according to the missing value to obtain the effective energy data.
7. The energy data cleaning method based on the energy network topology according to claim 6, wherein the step of obtaining a data similarity set based on the history monitoring set and the abnormal time monitoring set comprises:
calculating attribute similarity between each history monitoring amount and the abnormal moment monitoring amount; the attribute similarity comprises the similarity of the monitoring quantity of the total switch of the upstream branch and the similarity of the monitoring quantity of the switches of all the corresponding downstream branches; the attribute similarity is expressed as:
in the method, in the process of the invention,
d i (x i ,x i ′)＝|x i -x i ′|
d max ＝max{d i (x i ,x i ′),i＝1,2,...,n}
wherein x is i And x i 'represents the ith attribute value of the abnormal moment monitoring quantity x and the history monitoring quantity x', respectively; d, d i (x i ,x i ' indicates x i And x i ' absolute value of attribute deviation; d, d max The maximum attribute deviation absolute value of the abnormal moment monitoring quantity x and the historical monitoring quantity x' is represented; s is S i (x i ,x' i ) The attribute similarity of the ith attribute value of the monitoring quantity x at the abnormal moment and the historical monitoring quantity x' is represented; n represents the total number of attributes of the abnormal time monitoring quantity x and the history monitoring quantity x';
obtaining the corresponding monitoring quantity similarity according to the attribute similarity and the corresponding missing mark; the monitoring amount similarity is expressed as:
wherein Sim (x, x ') represents the similarity of the monitored quantity of the abnormal moment monitored quantity x and the historical monitored quantity x'; epsilon i And the missing mark of the ith attribute in the abnormal moment monitoring quantity is indicated.
8. An energy data cleaning system based on an energy network topology relationship, the system comprising:
the initial topology construction module is used for installing the corresponding switch state trackers on the switches of all branch nodes of the energy network and generating a corresponding initial switch branch topology diagram;
the real-time topology construction module is used for obtaining a switch branch real-time topological graph according to the switch states of the branch nodes and the corresponding initial switch branch topological graph, which are acquired in real time by each switch state tracker;
the network topology construction module is used for uploading the switch branch real-time topological graph to an energy monitoring system, and the energy monitoring system obtains an energy network real-time topological relation graph according to each switch state tracker and the corresponding switch branch real-time topological graph;
the topological relation updating module is used for responding to the change of the switching state of the branch node, updating a corresponding switching branch real-time topological graph by the switching state tracker, and uploading the updated switching branch real-time topological graph to the energy monitoring system so that the energy monitoring system updates the energy network real-time topological relation graph;
the topological relation comparison module is used for acquiring the switch branch real-time topological graph of each switch state tracker at fixed time, and comparing the switch branch real-time topological graph with the energy network real-time topological relation graph to obtain a topological relation comparison result;
and the energy data cleaning module is used for cleaning the corresponding energy data according to the topological relation comparison result to obtain effective energy data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310037977.XA CN115994136B (en) | 2023-01-10 | 2023-01-10 | Energy data cleaning method and system based on energy network topological relation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310037977.XA CN115994136B (en) | 2023-01-10 | 2023-01-10 | Energy data cleaning method and system based on energy network topological relation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115994136A true CN115994136A (en) | 2023-04-21 |
| CN115994136B CN115994136B (en) | 2023-09-05 |
Family
ID=85991728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310037977.XA Active CN115994136B (en) | 2023-01-10 | 2023-01-10 | Energy data cleaning method and system based on energy network topological relation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115994136B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110289119A1 (en) * | 2010-05-20 | 2011-11-24 | Sybase, Inc. | Methods and systems for monitoring server cloud topology and resources |
| US20150295774A1 (en) * | 2014-04-15 | 2015-10-15 | Centurylink Intellectual Property Llc | Topology Engine State Tracking |
| US20180068554A1 (en) * | 2016-09-06 | 2018-03-08 | Honeywell International Inc. | Systems and methods for generating a graphical representation of a fire system network and identifying network information for predicting network faults |
| CN111190955A (en) * | 2019-12-12 | 2020-05-22 | 西安交通大学 | Marketing, distribution and dispatching through checking method based on knowledge graph |
| CN112688310A (en) * | 2020-12-14 | 2021-04-20 | 国网河北省电力有限公司电力科学研究院 | Line loss analysis method and device applied to power distribution network |
| CN113014418A (en) * | 2021-01-29 | 2021-06-22 | 深圳市风云实业有限公司 | Fault diagnosis method based on network historical topology flow |
| US20210234922A1 (en) * | 2017-12-29 | 2021-07-29 | Electric Power Science & Research Institute Of State Grid Tianjin Electric Power Company | Method and device for identifying distribution network topology error |
| CN113507389A (en) * | 2021-07-08 | 2021-10-15 | 华北电力大学 | Power grid key node identification method and system |
| CN113904921A (en) * | 2021-10-21 | 2022-01-07 | 上海观安信息技术股份有限公司 | Dynamic network topological graph generating method, system, processing equipment and storage medium based on log and graph |
-
2023
- 2023-01-10 CN CN202310037977.XA patent/CN115994136B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110289119A1 (en) * | 2010-05-20 | 2011-11-24 | Sybase, Inc. | Methods and systems for monitoring server cloud topology and resources |
| US20150295774A1 (en) * | 2014-04-15 | 2015-10-15 | Centurylink Intellectual Property Llc | Topology Engine State Tracking |
| US20180068554A1 (en) * | 2016-09-06 | 2018-03-08 | Honeywell International Inc. | Systems and methods for generating a graphical representation of a fire system network and identifying network information for predicting network faults |
| US20210234922A1 (en) * | 2017-12-29 | 2021-07-29 | Electric Power Science & Research Institute Of State Grid Tianjin Electric Power Company | Method and device for identifying distribution network topology error |
| CN111190955A (en) * | 2019-12-12 | 2020-05-22 | 西安交通大学 | Marketing, distribution and dispatching through checking method based on knowledge graph |
| CN112688310A (en) * | 2020-12-14 | 2021-04-20 | 国网河北省电力有限公司电力科学研究院 | Line loss analysis method and device applied to power distribution network |
| CN113014418A (en) * | 2021-01-29 | 2021-06-22 | 深圳市风云实业有限公司 | Fault diagnosis method based on network historical topology flow |
| CN113507389A (en) * | 2021-07-08 | 2021-10-15 | 华北电力大学 | Power grid key node identification method and system |
| CN113904921A (en) * | 2021-10-21 | 2022-01-07 | 上海观安信息技术股份有限公司 | Dynamic network topological graph generating method, system, processing equipment and storage medium based on log and graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115994136B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766299B (en) | Data index abnormity monitoring method and system, storage medium and electronic equipment | |
| CN108600009B (en) | Network alarm root positioning method based on alarm data analysis | |
| EP3803593A1 (en) | Computing node failure and health prediction for cloud-based data center | |
| CN112150311B (en) | Method, device, computer equipment and storage medium for detecting abnormal energy consumption state | |
| US20190079965A1 (en) | Apparatus and method for real time analysis, predicting and reporting of anomalous database transaction log activity | |
| US8078913B2 (en) | Automated identification of performance crisis | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| US10444746B2 (en) | Method for managing subsystems of a process plant using a distributed control system | |
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| US9860109B2 (en) | Automatic alert generation | |
| CN110868241A (en) | Underground cable fault early warning method and device based on multiple models | |
| CN111666187B (en) | Method and apparatus for detecting abnormal response time | |
| CN111949429A (en) | Server fault monitoring method and system based on density clustering algorithm | |
| CN112380089A (en) | Data center monitoring and early warning method and system | |
| CN108334427B (en) | Fault diagnosis method and device in storage system | |
| CN115994136B (en) | Energy data cleaning method and system based on energy network topological relation | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| CN117234844A (en) | Cloud server abnormality management method and device, computer equipment and storage medium | |
| CN114266352B (en) | Model training result optimization method, device, storage medium and equipment | |
| CN113887676B (en) | Equipment fault early warning method, device, equipment and storage medium | |
| CN111625525A (en) | Environmental data repairing/filling method and system | |
| CN113487086B (en) | Method, device, computer equipment and medium for predicting residual service life of equipment | |
| Chen et al. | A multimode anomaly detection method based on oc-elm for aircraft engine system | |
| CN110689137B (en) | Parameter determination method, system, medium, and electronic device | |
| US20230008268A1 (en) | Extrapolated usage data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |